{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/improving-knowledge-graph-embedding-using","title":"Improving Knowledge Graph Embedding Using Simple Constraints","arxiv_id":"1805.02408","date":"2018-05-07","proceeding":"ACL 2018 7","authors":["Boyang Ding","Quan Wang","Bin Wang","Li Guo"],"abstract":"Embedding knowledge graphs (KGs) into continuous vector spaces is a focus of\ncurrent research. Early works performed this task via simple models developed\nover KG triples. Recent attempts focused on either designing more complicated\ntriple scoring models, or incorporating extra information beyond triples. This\npaper, by contrast, investigates the potential of using very simple constraints\nto improve KG embedding. We examine non-negativity constraints on entity\nrepresentations and approximate entailment constraints on relation\nrepresentations. The former help to learn compact and interpretable\nrepresentations for entities. The latter further encode regularities of logical\nentailment between relations into their distributed representations. These\nconstraints impose prior beliefs upon the structure of the embedding space,\nwithout negative impacts on efficiency or scalability. Evaluation on WordNet,\nFreebase, and DBpedia shows that our approach is simple yet surprisingly\neffective, significantly and consistently outperforming competitive baselines.\nThe constraints imposed indeed improve model interpretability, leading to a\nsubstantially increased structuring of the embedding space. Code and data are\navailable at https://github.com/iieir-km/ComplEx-NNE_AER.","url_abs":"http://arxiv.org/abs/1805.02408v2","url_pdf":"http://arxiv.org/pdf/1805.02408v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"improving-knowledge-graph-embedding-using","repo_url":"https://github.com/iieir-km/ComplEx-NNE_AER","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"knowledge-graph-embedding","task_name":"Knowledge Graph Embedding"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.02408","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}